期刊名称：International Journal of Advanced Computer Research
印刷版ISSN：2249-7277
电子版ISSN：2277-7970
出版年度：2019
卷号：9
期号：45
页码：379-385
DOI：10.19101/IJACR.2019.940067
出版社：Association of Computer Communication Education for National Triumph (ACCENT)
摘要：Rear-end vehicular collision due to illegally parked and unusually slow-moving vehicles on National Highways can be avoided if drivers can get alert messages and full information needed to make an objective judgment about what is ahead. A lot of work has been done on collision avoidance strategies using various networking techniques. IoT based solutions area recent research trend. The objective of this project is to develop an intelligent system that will identify illegally parked and the slow-moving vehicles on highways using the message queuing telemetry transport (MQTT) protocol that enables vehicles to exchange their real-time information, such as velocity and position, with the neighbouring vehicles through brokers (also called as servers). MQTT being a lightweight IoT protocol for machine to machine communication is useful for an effective data transfer between vehicles. An optimal algorithm has been developed to accurately identify every vehicle in the vicinity of the region of interest and to calculate both speed and position of the vehicle and transfer data from one vehicle to another vehicle. The new algorithm is implemented in a Raspberry Pi using a global positioning system (GPS) module. The results show that the collision avoidance system that uses MQTT protocol can accurately generate alert messages 90% of the time when there are only ten or less than ten vehicles which is also the case in most highways. Also, the system is easy to implement without requiring extra equipment. Hence the new technique can be used in various types of vehicles, especially cargo trucks and buses that use the highways frequently.
关键词：Collision avoidance; Vehicle to vehicle (V2V); Message queuing telemetry transport (MQTT); Global positioning system (GPS) speed; Compass direction; Hall effect sensor; Rotations per minute (RPM).
